Security audit

Kylinos Automated Testing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed desktop GUI testing guide whose powerful actions fit its testing purpose, though it should be used in a dedicated test environment.

Use this skill only when you intend an agent to operate a real desktop, install and remove the target app, take screenshots, and close target processes. Prefer a disposable VM or dedicated test account, keep sensitive windows closed, and provide the exact package and app scope before running tests.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill directs autonomous GUI control, process termination, screenshots, file operations, and desktop interaction in an active user session without a consolidated warning about risks to user data, privacy, or running applications. Because it operates on a live desktop and can kill processes or interact with dialogs, mistakes in window targeting or cleanup could cause data loss, unintended actions in unrelated applications, or capture of sensitive on-screen information.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly empowers an agent to install and uninstall software packages, which modifies the host system, but it does not require any explicit user confirmation, sandboxing, snapshotting, or warning about system impact. In the context of an autonomous desktop-testing skill, this creates a real risk of unintended package changes, dependency conflicts, or removal of software from a live user environment.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The description and operational instructions are entirely in Chinese and implicitly require interaction in that locale, but the skill does not offer users a language choice or state that Chinese is optional. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy issue.
Content: No source excerpt is available for this finding.